Research map / Video / Video segmentation and tracking
Temporal Modulation Network for Controllable Space-Time Video Super-Resolution
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use TMNet instead of Zooming Slow-Mo | STVSR · Vid4 | PSNR: 26.31 -> 26.43 | Helped |
| Use TMNet instead of Zooming Slow-Mo | STVSR · Vimeo-Fast | PSNR: 36.81 -> 37.04 | Helped |
| Use TMNet instead of Zooming Slow-Mo | STVSR · Vimeo-Medium | PSNR: 35.41 -> 35.60 | Helped |
| Use TMNet instead of Zooming Slow-Mo | STVSR · Vimeo-Slow | PSNR: 33.36 -> 33.51 | Helped |
| Add temporal modulation at all three PCD levels rather than one level only (ablation) | TMNet · Adobe240fps test | PSNR: 26.92 -> 26.95 | Helped |
| Use nonlinear TMB transformation rather than a linear layer (ablation) | TMNet · Adobe240fps test | PSNR: 26.93 -> 26.95 | Helped |
| Add LFC before global feature fusion (ablation) | TMNet · Vid4 | PSNR: 26.36 -> 26.43 | Helped |
| Add LFC before global feature fusion (ablation) | TMNet · Vimeo-Fast | PSNR: 36.87 -> 37.04 | Helped |
| Add LFC before global feature fusion (ablation) | TMNet · Vimeo-Medium | PSNR: 35.45 -> 35.60 | Helped |
| Add LFC before global feature fusion (ablation) | TMNet · Vimeo-Slow | PSNR: 33.40 -> 33.51 | Helped |
| Add initial feature maps F^L to the baseline (ablation) | TMNet · Vimeo-Fast | PSNR: 36.75 -> 36.87 | Helped |
| Add initial feature maps F^L to the baseline (ablation) | TMNet · Vid4 | PSNR: 26.33 -> 26.36 | Helped |
Closest papers by meaning
- RSTT: Real-Time Spatial Temporal Transformer for Space-Time Video Super-Resolution (CVPR 2022 · similarity 0.92)
- Time Without Time: Pseudo-Temporal Representation for Space-Time Super-Resolution (CVPR 2026 · similarity 0.91)
- Real-Time Video Super-Resolution With Spatio-Temporal Networks and Motion Compensation (CVPR 2017 · similarity 0.91)
- BF-STVSR: B-Splines and Fourier---Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution (CVPR 2025 · similarity 0.89)
- Event-based Video Super-Resolution via State Space Models (CVPR 2025 · similarity 0.87)
- EvSTVSR: Event Guided Space-Time Video Super-Resolution (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.